Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1145. Min Range: -1.1145

Max Act: 1.1145. Min Act: -0.0001

Data Index: 715121 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.1145. Min Range: -1.1145

Max Act: 1.0436. Min Act: -0.0001

Data Index: 1475493 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 1.1145. Min Range: -1.1145

Max Act: 1.0154. Min Act: -0.0001

Data Index: 1494482 (Python Code)

Max Activating Token Index: 361

Text #3

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9476. Min Act: -0.0001

Data Index: 1441583 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9638. Min Act: -0.0001

Data Index: 1552141 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1459292 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9374. Min Act: -0.0001

Data Index: 1362378 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9586. Min Act: -0.0001

Data Index: 741552 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1644590 (Python Code)

Max Activating Token Index: 668

Text #9

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9310. Min Act: -0.0001

Data Index: 1390094 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9316. Min Act: -0.0001

Data Index: 1441782 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9308. Min Act: -0.0001

Data Index: 1515611 (Python Code)

Max Activating Token Index: 524

Text #12

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8230. Min Act: -0.0001

Data Index: 1415698 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8944. Min Act: -0.0001

Data Index: 1380845 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1365139 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8110. Min Act: -0.0001

Data Index: 1386399 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9182. Min Act: -0.0001

Data Index: 1620179 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1643159 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.8339. Min Act: -0.0001

Data Index: 1603441 (Python Code)

Max Activating Token Index: 922

Text #19

Max Range: 1.1145. Min Range: -1.1145

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1586737 (Python Code)

Max Activating Token Index: 146